Compare two models
Select any two models. Input, output, cached, and context rarely move together — the cheaper model on one line isn't always the cheaper one on the next.
Description
A cost-efficient reasoning model from OpenAI with extended chain-of-thought processing optimized for STEM tasks, supporting configurable reasoning depth via the reasoning_effort parameter.
OpenAI's frontier model for complex professional workloads. 1M token context, text + image input, native computer use.
I/O price /1M
$0.55/$2.20
$5.00/$30.00
Input /1M
$0.55
$5.00
Output /1M
$2.20
$30.00
Cached in /1M
$0.275
$0.5
Context
200K
1M
Δ input since launch
—
—
Δ output since launch
—
—
Released
Jan 2025
Apr 2026
Status
—
—
Provider
OpenAI
OpenAI